While current monocular 3D face reconstruction methods can recover fine geometric details,
they suffer several limitations. Some methods produce faces that cannot be realistically …

As 3D facial avatars become more widely used for communication, it is critical that they
faithfully convey emotion. Unfortunately, the best recent methods that regress parametric 3D …

We present PyMAF-X, a regression-based approach to recovering a parametric full-body
model from a single image. This task is very challenging since minor parametric deviation …

Face reconstruction and tracking is a building block of numerous applications in AR/VR,
human-machine interaction, as well as medical applications. Most of these applications rely …

To understand how people look, interact, or perform tasks, we need to quickly and
accurately capture their 3D body, face, and hands together from an RGB image. Most …

We present a new loss function, namely Wing loss, for robust facial landmark localisation
with Convolutional Neural Networks (CNNs). We first compare and analyse different loss …

The estimation of 3D face shape from a single image must be robust to variations in lighting,
head pose, expression, facial hair, makeup, and occlusions. Robustness requires a large …

We propose a method to learn 3D deformable object categories from raw single-view
images, without external supervision. The method is based on an autoencoder that factors …

We present SfSNet, an end-to-end learning framework for producing an accurate
decomposition of an unconstrained human face image into shape, reflectance and …

Abstract 3D face reconstruction is the most captivating topic in biometrics with the advent of
deep learning and readily available graphical processing units. This paper explores the …